© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78029
    Prev
    Next
    INDEX
    Explanations

    Spring MVC filenames and keywords

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is picking out version‐number tokens (especially dotted numeric strings) in Maven/POM XML.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bean
    -0.90
    GUILayout
    -0.88
    bean
    -0.80
    EditorGUILayout
    -0.73
    싱
    -0.72
    Louisiana
    -0.70
    posable
    -0.68
     beans
    -0.68
    closest
    -0.67
    änning
    -0.67
    POSITIVE LOGITS
     Thyme
    0.99
    fragments
    0.96
     thyme
    0.93
     Principal
    0.82
    Principal
    0.79
    redirect
    0.79
     Sock
    0.78
     Iterable
    0.77
    AttributeName
    0.77
    AZIONI
    0.76
    Activations Density 0.026%

    No Known Activations